Triple
T22149084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dil Apna Aur Preet Parai |
E547366
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Kishore Sahu |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kishore Sahu | Statement: [Dil Apna Aur Preet Parai, director, Kishore Sahu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kishore Sahu Context triple: [Dil Apna Aur Preet Parai, director, Kishore Sahu]
-
A.
Kishore Sahu
chosen
Kishore Sahu was a prominent Indian film director, actor, and producer known for his influential work during the Golden Age of Hindi cinema.
-
B.
Manoj Sinha
Manoj Sinha is an Indian politician from the Bharatiya Janata Party who has served as a Member of Parliament and as the Lieutenant Governor of Jammu and Kashmir.
-
C.
Kishor Kadam
Kishor Kadam is an Indian actor and Marathi poet known for his character roles in Hindi and Marathi cinema.
-
D.
Kumar Chandrak
Kumar Chandrak is a literary award given in recognition of notable contributions to Gujarati literature.
-
E.
Ashok Kumar
Ashok Kumar was a pioneering and acclaimed Indian film actor, often regarded as one of the first superstars of Hindi cinema.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f2c0e881909c3488bb5eb5959d |
completed | April 28, 2026, 9:43 p.m. |
Created at: April 16, 2026, 8:33 p.m.